Simple CUDA Runtime (#480)

* factor out opencl runtime

* don't use CL outside the runtime

* cuda runtime adds

* final_dimension

* tests pass with CUDA backend

* more cuda

* cuda simpler

* retain old functionality

* linter and typing

* move globalcounters out of runtimes

* oops, GlobalCounters in cuda

* MAX_OUTPUT_SHAPE=3 is fine for CUDA

setup.py

@@ -24,6 +24,7 @@ setup(name='tinygrad',
       extras_require={
         'gpu': ["pyopencl", "six"],
         'llvm': ["llvmlite"],
+        'cuda': ["pycuda"],
         'testing': [
             "pytest",
             "torch~=1.11.0",